github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 06:31:50 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #5352] [BUG]: Gemma2 crashes on run. #81031

New Issue
Closed
opened 2026-05-09 10:12:27 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-09 10:12:27 -05:00
Owner
Copy Link

Originally created by @ghost on GitHub (Jun 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5352

What is the issue?

Running the following in sequence crashes with the below output.

  1. ollama pull gemma2
  2. ollama run gemma2
    Output:
    Error: llama runner process has terminated: signal: aborted (core dumped)
    Coredumpctl:
           PID: 3776 (ollama_llama_se)
           UID: 61547 (ollama)
           GID: 61547 (ollama)
        Signal: 6 (ABRT)
     Timestamp: Fri 2024-06-28 12:19:15 AEST (1min 3s ago)
  Command Line: /tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server --model /var/lib/ollama/models/blobs/sha256-e84ed7399c82fbf7dbd6cdef3f12d356c3cdb5512e5d8b2a9898080cbcdd72e5 --ctx-size 2048 --b>
    Executable: /tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server
 Control Group: /system.slice/ollama.service
          Unit: ollama.service
         Slice: system.slice
       Boot ID: bba51a07162c412d9a05f2b6cb3cd45d
    Machine ID: dcf2fcf728b7460d8f2ef435eaecf8e0
      Hostname: nixos
       Storage: /var/lib/systemd/coredump/core.ollama_llama_se.61547.bba51a07162c412d9a05f2b6cb3cd45d.3776.1719541155000000.zst (inaccessible)
       Message: Process 3776 (ollama_llama_se) of user 61547 dumped core.
                
                Module /tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server without build-id.
                Module /tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server
                Module /tmp/ollama3483777596/runners/cuda_v12/libcublasLt.so.12 without build-id.
                Module /tmp/ollama3483777596/runners/cuda_v12/libcublasLt.so.12
                Module /tmp/ollama3483777596/runners/cuda_v12/libcublas.so.12 without build-id.
                Module /tmp/ollama3483777596/runners/cuda_v12/libcublas.so.12
                Module /tmp/ollama3483777596/runners/cuda_v12/libcudart.so.12 without build-id.
                Module /tmp/ollama3483777596/runners/cuda_v12/libcudart.so.12
                Module libgcc_s.so.1 without build-id.
                Module libstdc++.so.6 without build-id.
                Stack trace of thread 3776:
                #0  0x00007ff2bb8a1efc __pthread_kill_implementation (libc.so.6 + 0x8fefc)
                #1  0x00007ff2bb851e96 raise (libc.so.6 + 0x3fe96)
                #2  0x00007ff2bb83a935 abort (libc.so.6 + 0x28935)
                #3  0x00007ff28fca9a89 _ZN9__gnu_cxx27__verbose_terminate_handlerEv.cold (libstdc++.so.6 + 0xa9a89)
                #4  0x00007ff28fcb4f8a _ZN10__cxxabiv111__terminateEPFvvE (libstdc++.so.6 + 0xb4f8a)
                #5  0x00007ff28fcb4ff5 _ZSt9terminatev (libstdc++.so.6 + 0xb4ff5)
                #6  0x00007ff28fcb5298 __cxa_rethrow (libstdc++.so.6 + 0xb5298)
                #7  0x000000000042bf81 n/a (/tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server + 0x2bf81)
                #8  0x0000000000504deb n/a (/tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server + 0x104deb)
                #9  0x0000000000499447 n/a (/tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server + 0x99447)
                #10 0x000000000042e566 n/a (/tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server + 0x2e566)
                #11 0x00007ff2bb83c10e __libc_start_call_main (libc.so.6 + 0x2a10e)
                #12 0x00007ff2bb83c1c9 __libc_start_main@@GLIBC_2.34 (libc.so.6 + 0x2a1c9)
                #13 0x00000000004469f5 n/a (/tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server + 0x469f5)
                ELF object binary architecture: AMD x86-64

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.45

Originally created by @ghost on GitHub (Jun 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5352 ### What is the issue? Running the following in sequence crashes with the below output. 1. `ollama pull gemma2` 2. `ollama run gemma2` Output: `Error: llama runner process has terminated: signal: aborted (core dumped)` Coredumpctl: ``` PID: 3776 (ollama_llama_se) UID: 61547 (ollama) GID: 61547 (ollama) Signal: 6 (ABRT) Timestamp: Fri 2024-06-28 12:19:15 AEST (1min 3s ago) Command Line: /tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server --model /var/lib/ollama/models/blobs/sha256-e84ed7399c82fbf7dbd6cdef3f12d356c3cdb5512e5d8b2a9898080cbcdd72e5 --ctx-size 2048 --b> Executable: /tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server Control Group: /system.slice/ollama.service Unit: ollama.service Slice: system.slice Boot ID: bba51a07162c412d9a05f2b6cb3cd45d Machine ID: dcf2fcf728b7460d8f2ef435eaecf8e0 Hostname: nixos Storage: /var/lib/systemd/coredump/core.ollama_llama_se.61547.bba51a07162c412d9a05f2b6cb3cd45d.3776.1719541155000000.zst (inaccessible) Message: Process 3776 (ollama_llama_se) of user 61547 dumped core. Module /tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server without build-id. Module /tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server Module /tmp/ollama3483777596/runners/cuda_v12/libcublasLt.so.12 without build-id. Module /tmp/ollama3483777596/runners/cuda_v12/libcublasLt.so.12 Module /tmp/ollama3483777596/runners/cuda_v12/libcublas.so.12 without build-id. Module /tmp/ollama3483777596/runners/cuda_v12/libcublas.so.12 Module /tmp/ollama3483777596/runners/cuda_v12/libcudart.so.12 without build-id. Module /tmp/ollama3483777596/runners/cuda_v12/libcudart.so.12 Module libgcc_s.so.1 without build-id. Module libstdc++.so.6 without build-id. Stack trace of thread 3776: #0 0x00007ff2bb8a1efc __pthread_kill_implementation (libc.so.6 + 0x8fefc) #1 0x00007ff2bb851e96 raise (libc.so.6 + 0x3fe96) #2 0x00007ff2bb83a935 abort (libc.so.6 + 0x28935) #3 0x00007ff28fca9a89 _ZN9__gnu_cxx27__verbose_terminate_handlerEv.cold (libstdc++.so.6 + 0xa9a89) #4 0x00007ff28fcb4f8a _ZN10__cxxabiv111__terminateEPFvvE (libstdc++.so.6 + 0xb4f8a) #5 0x00007ff28fcb4ff5 _ZSt9terminatev (libstdc++.so.6 + 0xb4ff5) #6 0x00007ff28fcb5298 __cxa_rethrow (libstdc++.so.6 + 0xb5298) #7 0x000000000042bf81 n/a (/tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server + 0x2bf81) #8 0x0000000000504deb n/a (/tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server + 0x104deb) #9 0x0000000000499447 n/a (/tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server + 0x99447) #10 0x000000000042e566 n/a (/tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server + 0x2e566) #11 0x00007ff2bb83c10e __libc_start_call_main (libc.so.6 + 0x2a10e) #12 0x00007ff2bb83c1c9 __libc_start_main@@GLIBC_2.34 (libc.so.6 + 0x2a1c9) #13 0x00000000004469f5 n/a (/tmp/ollama3483777596/runners/cuda_v12/ollama_llama_server + 0x469f5) ELF object binary architecture: AMD x86-64 ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.45
GiteaMirror added the bug label 2026-05-09 10:12:27 -05:00
GiteaMirror commented 2026-05-09 10:12:30 -05:00
Author
Owner
Copy Link

@Forevery1 commented on GitHub (Jun 28, 2024):

image
<!-- gh-comment-id:2195992198 --> @Forevery1 commented on GitHub (Jun 28, 2024): <img width="848" alt="image" src="https://github.com/ollama/ollama/assets/19872771/0387bf17-52b5-488e-975e-b6343a1f7b02">
GiteaMirror commented 2026-05-09 10:12:31 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Jun 28, 2024):

@Forevery1
Understood, I'm on NixOS unstable and ollama has not been updated yet.

<!-- gh-comment-id:2196000017 --> @ghost commented on GitHub (Jun 28, 2024): @Forevery1 Understood, I'm on NixOS unstable and ollama has not been updated yet.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#81031
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?